Difference between revisions of "2016 Winter Project Week/Projects/BatchImageAnalysis"

From NAMIC Wiki
Jump to: navigation, search
Line 45: Line 45:
 
* feature matching O(log N) indexing (< 1 second per image)
 
* feature matching O(log N) indexing (< 1 second per image)
  
* code (Windows, Linux, Max)  and read me
+
* 3D SIFT-Rank code (Windows, Linux, Max)  and read me
 
http://www.matthewtoews.com/fba/featExtract1.5.zip
 
http://www.matthewtoews.com/fba/featExtract1.5.zip
  

Revision as of 06:40, 8 January 2016

Home < 2016 Winter Project Week < Projects < BatchImageAnalysis
3D SIFT Lung Features

Key Investigators

  • Kalli Retzepi (MGH)
  • Yangming Ou (MGH)
  • Matt Toews (ETS)
  • Steve Pieper (BWH)
  • Sandy Wells (BWH)
  • Randy Gollub (MGH)

Project Description

Objective Approach and Plan Progress and Next Steps
  • Run feature detection code over a collection of medical images pulled from PACS
  • Investigate a collection of ADC maps of neonates (diffusion MR)
  • Patients labeled with age and health status (normal, mildly abnormal, severely abnormal)
  • Use 3D SIFT code to see if health status can be detected in images
  • (if time) try text analysis of radiology reports
  • Use deidentified cohort of neonate images collected from MGH
  • Install data and software on AWS, try StarCluster
  • Explore visualization options
  • (if time) integrate image features with analysis of radiology report text

Algorithm

  • feature extraction (20 seconds per image)
  • feature matching O(log N) indexing (< 1 second per image)
  • 3D SIFT-Rank code (Windows, Linux, Max) and read me

http://www.matthewtoews.com/fba/featExtract1.5.zip

Leave-one-out classification rate for HIE: moderate vs normal: 73%

Data 231 subjects, Apparent Diffusion Coefficient (ADC) images.

Features Extracted in ADC MRI Volume

Image_%282%29.png